© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15615
    Prev
    Next
    INDEX
    Explanations

    the number "192" alone or as part of a longer number

    oai_token-act-pair · gemini-2.0-flash

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndroidJUnit
    -1.09
    EndInit
    -0.98
    Personendaten
    -0.95
    AddTagHelper
    -0.93
     Signalez
    -0.91
     Roskov
    -0.91
     '\\;'
    -0.90
    GEBURTSDATUM
    -0.86
    tagHelperRunner
    -0.84
     "..\..\
    -0.84
    POSITIVE LOGITS
    9
    0.62
    4
    0.57
    7
    0.48
    8
    0.47
    5
    0.47
    3
    0.45
     lie
    0.43
    st
    0.41
    6
    0.40
    ฐ
    0.34
    Activations Density 0.552%

    No Known Activations